RedTeam Arena
Not in model cards
Players get 60 seconds to make a model say a target word. An extended Elo ranks players, models and target prompts, with models ranked by resistance.
Built with Pliny and the BASI community. About 8,000 people played in the first week. Arena notes that resistance trades off with controllability.
- Level
- Everyday Most adults, without training
- Scored
- Ranked by matches Models play against each other, and the results become ratings.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for RedTeam Arena yet.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy.
Muse Spark Open 98.1% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%